Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    dates mentioned in the context of historical events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    abilia
    -0.76
    bars
    -0.74
    avascript
    -0.74
    ources
    -0.73
    ifles
    -0.73
     presently
    -0.73
    erate
    -0.72
     lately
    -0.72
    bags
    -0.71
     nowadays
    -0.68
    POSITIVE LOGITS
     edition
    0.93
     census
    0.87
     Nobel
    0.85
     arrival
    0.85
     eruption
    0.84
     uprising
    0.83
    -'
    0.83
     midterm
    0.81
     incarnation
    0.81
     presidential
    0.80
    Act Density 0.077%

    No Known Activations